- Home
- Agent skills
- Hyperresearch
Hyperresearch
Multi-step deep research pipeline for Claude Code and Codex
What it is
A research harness that runs a 16-step pipeline from a single prompt and produces a report with audited claims and source provenance. Every source it reads is stored in a persistent, searchable local vault so later sessions can reuse it. Installs as a skill with subagents and a hook that prevents skipped steps.
Good for
- Write a sourced report on a technical topic
- Build a reusable vault of read sources
- Audit claims against their citations
Install or run
pip install hyperresearchCommand as given in the project README. Read the repository before you run anything on your machine.
What you need
Python; Claude Code or Codex with web access
Sources
- https://github.com/jordan-gibbs/hyperresearch (project README, read 10 Nov 2026)
- https://api.github.com/repos/jordan-gibbs/hyperresearch (GitHub API, read 13 Nov 2026)
The summary is ours, written from the README. Spotted an error? See how we work.